mikeleske commited on
Commit
9c5107f
1 Parent(s): 7fbdea7

Upload 5 files

Browse files
config.json ADDED
@@ -0,0 +1,91 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": "9562f3fdc38f09b92594864c5e98264f1bfbca33",
3
+ "_name_or_path": "togethercomputer/evo-1-131k-base",
4
+ "architectures": [
5
+ "StripedHyenaModelForCausalLM"
6
+ ],
7
+ "attn_layer_idxs": [
8
+ 8,
9
+ 16,
10
+ 24
11
+ ],
12
+ "auto_map": {
13
+ "AutoConfig": "togethercomputer/evo-1-131k-base--configuration_hyena.StripedHyenaConfig",
14
+ "AutoModelForCausalLM": "togethercomputer/evo-1-131k-base--modeling_hyena.StripedHyenaModelForCausalLM",
15
+ "AutoTokenizer": [
16
+ "togethercomputer/evo-1-131k-base--tokenizer.ByteTokenizer",
17
+ null
18
+ ]
19
+ },
20
+ "column_split": false,
21
+ "column_split_hyena": true,
22
+ "eps": 1e-06,
23
+ "final_norm": true,
24
+ "hidden_size": 4096,
25
+ "hyena_filter_groups": 1,
26
+ "hyena_layer_idxs": [
27
+ 0,
28
+ 1,
29
+ 2,
30
+ 3,
31
+ 4,
32
+ 5,
33
+ 6,
34
+ 7,
35
+ 9,
36
+ 10,
37
+ 11,
38
+ 12,
39
+ 13,
40
+ 14,
41
+ 15,
42
+ 17,
43
+ 18,
44
+ 19,
45
+ 20,
46
+ 21,
47
+ 22,
48
+ 23,
49
+ 25,
50
+ 26,
51
+ 27,
52
+ 28,
53
+ 29,
54
+ 30,
55
+ 31
56
+ ],
57
+ "inference_mode": false,
58
+ "inner_mlp_size": 10928,
59
+ "log_intermediate_values": false,
60
+ "make_vocab_size_divisible_by": 8,
61
+ "max_seqlen": 131072,
62
+ "mha_out_proj_bias": true,
63
+ "mlp_activation": "gelu",
64
+ "model_parallel_size": 1,
65
+ "model_type": "stripedhyena",
66
+ "num_attention_heads": 32,
67
+ "num_filters": 4096,
68
+ "num_layers": 32,
69
+ "pipe_parallel_size": 1,
70
+ "prefill_style": "fft",
71
+ "proj_groups": 1,
72
+ "qkv_proj_bias": true,
73
+ "rotary_emb_base": 10000,
74
+ "rotary_emb_scaling_factor": 16,
75
+ "short_filter_bias": true,
76
+ "short_filter_length": 3,
77
+ "smeared_gqa": false,
78
+ "split_k0": true,
79
+ "state_size": 8,
80
+ "tie_embeddings": true,
81
+ "torch_dtype": "bfloat16",
82
+ "transformers_version": null,
83
+ "use_cache": true,
84
+ "use_flash_attention_2": true,
85
+ "use_flash_attn": true,
86
+ "use_flash_depthwise": false,
87
+ "use_flash_rmsnorm": false,
88
+ "use_flashfft": false,
89
+ "use_interpolated_rotary_pos_emb": true,
90
+ "vocab_size": 512
91
+ }
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "transformers_version": "4.40.1"
4
+ }
pytorch_model-00001-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ae71d1a896e490da51751ef0ef2ed00879f66824259653538a6a496e3cd3243
3
+ size 4980102165
pytorch_model-00003-of-00003.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2591139f7373fc6be3fd9712cfb1c2ad9364bbb3ee5edf9331e02188d1598272
3
+ size 3003328882
pytorch_model.bin.index.json ADDED
@@ -0,0 +1,446 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 12913164672
4
+ },
5
+ "weight_map": {
6
+ "backbone.blocks.0.filter.D": "pytorch_model-00001-of-00003.bin",
7
+ "backbone.blocks.0.filter.poles": "pytorch_model-00001-of-00003.bin",
8
+ "backbone.blocks.0.filter.residues": "pytorch_model-00001-of-00003.bin",
9
+ "backbone.blocks.0.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
10
+ "backbone.blocks.0.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
11
+ "backbone.blocks.0.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
12
+ "backbone.blocks.0.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
13
+ "backbone.blocks.0.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
14
+ "backbone.blocks.0.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
15
+ "backbone.blocks.0.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
16
+ "backbone.blocks.0.post_norm.scale": "pytorch_model-00001-of-00003.bin",
17
+ "backbone.blocks.0.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
18
+ "backbone.blocks.0.projections.bias": "pytorch_model-00001-of-00003.bin",
19
+ "backbone.blocks.0.projections.weight": "pytorch_model-00001-of-00003.bin",
20
+ "backbone.blocks.1.filter.D": "pytorch_model-00001-of-00003.bin",
21
+ "backbone.blocks.1.filter.poles": "pytorch_model-00001-of-00003.bin",
22
+ "backbone.blocks.1.filter.residues": "pytorch_model-00001-of-00003.bin",
23
+ "backbone.blocks.1.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
24
+ "backbone.blocks.1.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
25
+ "backbone.blocks.1.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
26
+ "backbone.blocks.1.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
27
+ "backbone.blocks.1.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
28
+ "backbone.blocks.1.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
29
+ "backbone.blocks.1.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
30
+ "backbone.blocks.1.post_norm.scale": "pytorch_model-00001-of-00003.bin",
31
+ "backbone.blocks.1.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
32
+ "backbone.blocks.1.projections.bias": "pytorch_model-00001-of-00003.bin",
33
+ "backbone.blocks.1.projections.weight": "pytorch_model-00001-of-00003.bin",
34
+ "backbone.blocks.10.filter.D": "pytorch_model-00001-of-00003.bin",
35
+ "backbone.blocks.10.filter.poles": "pytorch_model-00001-of-00003.bin",
36
+ "backbone.blocks.10.filter.residues": "pytorch_model-00001-of-00003.bin",
37
+ "backbone.blocks.10.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
38
+ "backbone.blocks.10.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
39
+ "backbone.blocks.10.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
40
+ "backbone.blocks.10.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
41
+ "backbone.blocks.10.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
42
+ "backbone.blocks.10.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
43
+ "backbone.blocks.10.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
44
+ "backbone.blocks.10.post_norm.scale": "pytorch_model-00001-of-00003.bin",
45
+ "backbone.blocks.10.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
46
+ "backbone.blocks.10.projections.bias": "pytorch_model-00001-of-00003.bin",
47
+ "backbone.blocks.10.projections.weight": "pytorch_model-00001-of-00003.bin",
48
+ "backbone.blocks.11.filter.D": "pytorch_model-00001-of-00003.bin",
49
+ "backbone.blocks.11.filter.poles": "pytorch_model-00001-of-00003.bin",
50
+ "backbone.blocks.11.filter.residues": "pytorch_model-00001-of-00003.bin",
51
+ "backbone.blocks.11.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
52
+ "backbone.blocks.11.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
53
+ "backbone.blocks.11.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
54
+ "backbone.blocks.11.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
55
+ "backbone.blocks.11.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
56
+ "backbone.blocks.11.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
57
+ "backbone.blocks.11.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
58
+ "backbone.blocks.11.post_norm.scale": "pytorch_model-00001-of-00003.bin",
59
+ "backbone.blocks.11.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
60
+ "backbone.blocks.11.projections.bias": "pytorch_model-00001-of-00003.bin",
61
+ "backbone.blocks.11.projections.weight": "pytorch_model-00001-of-00003.bin",
62
+ "backbone.blocks.12.filter.D": "pytorch_model-00001-of-00003.bin",
63
+ "backbone.blocks.12.filter.poles": "pytorch_model-00001-of-00003.bin",
64
+ "backbone.blocks.12.filter.residues": "pytorch_model-00001-of-00003.bin",
65
+ "backbone.blocks.12.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
66
+ "backbone.blocks.12.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
67
+ "backbone.blocks.12.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
68
+ "backbone.blocks.12.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
69
+ "backbone.blocks.12.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
70
+ "backbone.blocks.12.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
71
+ "backbone.blocks.12.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
72
+ "backbone.blocks.12.post_norm.scale": "pytorch_model-00001-of-00003.bin",
73
+ "backbone.blocks.12.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
74
+ "backbone.blocks.12.projections.bias": "pytorch_model-00001-of-00003.bin",
75
+ "backbone.blocks.12.projections.weight": "pytorch_model-00001-of-00003.bin",
76
+ "backbone.blocks.13.filter.D": "pytorch_model-00002-of-00003.bin",
77
+ "backbone.blocks.13.filter.poles": "pytorch_model-00002-of-00003.bin",
78
+ "backbone.blocks.13.filter.residues": "pytorch_model-00002-of-00003.bin",
79
+ "backbone.blocks.13.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
80
+ "backbone.blocks.13.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
81
+ "backbone.blocks.13.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
82
+ "backbone.blocks.13.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
83
+ "backbone.blocks.13.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
84
+ "backbone.blocks.13.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
85
+ "backbone.blocks.13.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
86
+ "backbone.blocks.13.post_norm.scale": "pytorch_model-00002-of-00003.bin",
87
+ "backbone.blocks.13.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
88
+ "backbone.blocks.13.projections.bias": "pytorch_model-00002-of-00003.bin",
89
+ "backbone.blocks.13.projections.weight": "pytorch_model-00002-of-00003.bin",
90
+ "backbone.blocks.14.filter.D": "pytorch_model-00002-of-00003.bin",
91
+ "backbone.blocks.14.filter.poles": "pytorch_model-00002-of-00003.bin",
92
+ "backbone.blocks.14.filter.residues": "pytorch_model-00002-of-00003.bin",
93
+ "backbone.blocks.14.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
94
+ "backbone.blocks.14.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
95
+ "backbone.blocks.14.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
96
+ "backbone.blocks.14.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
97
+ "backbone.blocks.14.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
98
+ "backbone.blocks.14.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
99
+ "backbone.blocks.14.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
100
+ "backbone.blocks.14.post_norm.scale": "pytorch_model-00002-of-00003.bin",
101
+ "backbone.blocks.14.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
102
+ "backbone.blocks.14.projections.bias": "pytorch_model-00002-of-00003.bin",
103
+ "backbone.blocks.14.projections.weight": "pytorch_model-00002-of-00003.bin",
104
+ "backbone.blocks.15.filter.D": "pytorch_model-00002-of-00003.bin",
105
+ "backbone.blocks.15.filter.poles": "pytorch_model-00002-of-00003.bin",
106
+ "backbone.blocks.15.filter.residues": "pytorch_model-00002-of-00003.bin",
107
+ "backbone.blocks.15.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
108
+ "backbone.blocks.15.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
109
+ "backbone.blocks.15.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
110
+ "backbone.blocks.15.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
111
+ "backbone.blocks.15.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
112
+ "backbone.blocks.15.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
113
+ "backbone.blocks.15.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
114
+ "backbone.blocks.15.post_norm.scale": "pytorch_model-00002-of-00003.bin",
115
+ "backbone.blocks.15.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
116
+ "backbone.blocks.15.projections.bias": "pytorch_model-00002-of-00003.bin",
117
+ "backbone.blocks.15.projections.weight": "pytorch_model-00002-of-00003.bin",
118
+ "backbone.blocks.16.inner_mha_cls.Wqkv.bias": "pytorch_model-00002-of-00003.bin",
119
+ "backbone.blocks.16.inner_mha_cls.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
120
+ "backbone.blocks.16.inner_mha_cls.out_proj.bias": "pytorch_model-00002-of-00003.bin",
121
+ "backbone.blocks.16.inner_mha_cls.out_proj.weight": "pytorch_model-00002-of-00003.bin",
122
+ "backbone.blocks.16.inner_mha_cls.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
123
+ "backbone.blocks.16.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
124
+ "backbone.blocks.16.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
125
+ "backbone.blocks.16.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
126
+ "backbone.blocks.16.post_norm.scale": "pytorch_model-00002-of-00003.bin",
127
+ "backbone.blocks.16.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
128
+ "backbone.blocks.17.filter.D": "pytorch_model-00002-of-00003.bin",
129
+ "backbone.blocks.17.filter.poles": "pytorch_model-00002-of-00003.bin",
130
+ "backbone.blocks.17.filter.residues": "pytorch_model-00002-of-00003.bin",
131
+ "backbone.blocks.17.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
132
+ "backbone.blocks.17.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
133
+ "backbone.blocks.17.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
134
+ "backbone.blocks.17.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
135
+ "backbone.blocks.17.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
136
+ "backbone.blocks.17.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
137
+ "backbone.blocks.17.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
138
+ "backbone.blocks.17.post_norm.scale": "pytorch_model-00002-of-00003.bin",
139
+ "backbone.blocks.17.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
140
+ "backbone.blocks.17.projections.bias": "pytorch_model-00002-of-00003.bin",
141
+ "backbone.blocks.17.projections.weight": "pytorch_model-00002-of-00003.bin",
142
+ "backbone.blocks.18.filter.D": "pytorch_model-00002-of-00003.bin",
143
+ "backbone.blocks.18.filter.poles": "pytorch_model-00002-of-00003.bin",
144
+ "backbone.blocks.18.filter.residues": "pytorch_model-00002-of-00003.bin",
145
+ "backbone.blocks.18.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
146
+ "backbone.blocks.18.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
147
+ "backbone.blocks.18.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
148
+ "backbone.blocks.18.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
149
+ "backbone.blocks.18.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
150
+ "backbone.blocks.18.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
151
+ "backbone.blocks.18.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
152
+ "backbone.blocks.18.post_norm.scale": "pytorch_model-00002-of-00003.bin",
153
+ "backbone.blocks.18.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
154
+ "backbone.blocks.18.projections.bias": "pytorch_model-00002-of-00003.bin",
155
+ "backbone.blocks.18.projections.weight": "pytorch_model-00002-of-00003.bin",
156
+ "backbone.blocks.19.filter.D": "pytorch_model-00002-of-00003.bin",
157
+ "backbone.blocks.19.filter.poles": "pytorch_model-00002-of-00003.bin",
158
+ "backbone.blocks.19.filter.residues": "pytorch_model-00002-of-00003.bin",
159
+ "backbone.blocks.19.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
160
+ "backbone.blocks.19.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
161
+ "backbone.blocks.19.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
162
+ "backbone.blocks.19.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
163
+ "backbone.blocks.19.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
164
+ "backbone.blocks.19.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
165
+ "backbone.blocks.19.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
166
+ "backbone.blocks.19.post_norm.scale": "pytorch_model-00002-of-00003.bin",
167
+ "backbone.blocks.19.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
168
+ "backbone.blocks.19.projections.bias": "pytorch_model-00002-of-00003.bin",
169
+ "backbone.blocks.19.projections.weight": "pytorch_model-00002-of-00003.bin",
170
+ "backbone.blocks.2.filter.D": "pytorch_model-00001-of-00003.bin",
171
+ "backbone.blocks.2.filter.poles": "pytorch_model-00001-of-00003.bin",
172
+ "backbone.blocks.2.filter.residues": "pytorch_model-00001-of-00003.bin",
173
+ "backbone.blocks.2.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
174
+ "backbone.blocks.2.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
175
+ "backbone.blocks.2.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
176
+ "backbone.blocks.2.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
177
+ "backbone.blocks.2.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
178
+ "backbone.blocks.2.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
179
+ "backbone.blocks.2.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
180
+ "backbone.blocks.2.post_norm.scale": "pytorch_model-00001-of-00003.bin",
181
+ "backbone.blocks.2.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
182
+ "backbone.blocks.2.projections.bias": "pytorch_model-00001-of-00003.bin",
183
+ "backbone.blocks.2.projections.weight": "pytorch_model-00001-of-00003.bin",
184
+ "backbone.blocks.20.filter.D": "pytorch_model-00002-of-00003.bin",
185
+ "backbone.blocks.20.filter.poles": "pytorch_model-00002-of-00003.bin",
186
+ "backbone.blocks.20.filter.residues": "pytorch_model-00002-of-00003.bin",
187
+ "backbone.blocks.20.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
188
+ "backbone.blocks.20.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
189
+ "backbone.blocks.20.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
190
+ "backbone.blocks.20.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
191
+ "backbone.blocks.20.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
192
+ "backbone.blocks.20.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
193
+ "backbone.blocks.20.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
194
+ "backbone.blocks.20.post_norm.scale": "pytorch_model-00002-of-00003.bin",
195
+ "backbone.blocks.20.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
196
+ "backbone.blocks.20.projections.bias": "pytorch_model-00002-of-00003.bin",
197
+ "backbone.blocks.20.projections.weight": "pytorch_model-00002-of-00003.bin",
198
+ "backbone.blocks.21.filter.D": "pytorch_model-00002-of-00003.bin",
199
+ "backbone.blocks.21.filter.poles": "pytorch_model-00002-of-00003.bin",
200
+ "backbone.blocks.21.filter.residues": "pytorch_model-00002-of-00003.bin",
201
+ "backbone.blocks.21.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
202
+ "backbone.blocks.21.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
203
+ "backbone.blocks.21.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
204
+ "backbone.blocks.21.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
205
+ "backbone.blocks.21.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
206
+ "backbone.blocks.21.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
207
+ "backbone.blocks.21.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
208
+ "backbone.blocks.21.post_norm.scale": "pytorch_model-00002-of-00003.bin",
209
+ "backbone.blocks.21.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
210
+ "backbone.blocks.21.projections.bias": "pytorch_model-00002-of-00003.bin",
211
+ "backbone.blocks.21.projections.weight": "pytorch_model-00002-of-00003.bin",
212
+ "backbone.blocks.22.filter.D": "pytorch_model-00002-of-00003.bin",
213
+ "backbone.blocks.22.filter.poles": "pytorch_model-00002-of-00003.bin",
214
+ "backbone.blocks.22.filter.residues": "pytorch_model-00002-of-00003.bin",
215
+ "backbone.blocks.22.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
216
+ "backbone.blocks.22.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
217
+ "backbone.blocks.22.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
218
+ "backbone.blocks.22.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
219
+ "backbone.blocks.22.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
220
+ "backbone.blocks.22.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
221
+ "backbone.blocks.22.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
222
+ "backbone.blocks.22.post_norm.scale": "pytorch_model-00002-of-00003.bin",
223
+ "backbone.blocks.22.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
224
+ "backbone.blocks.22.projections.bias": "pytorch_model-00002-of-00003.bin",
225
+ "backbone.blocks.22.projections.weight": "pytorch_model-00002-of-00003.bin",
226
+ "backbone.blocks.23.filter.D": "pytorch_model-00002-of-00003.bin",
227
+ "backbone.blocks.23.filter.poles": "pytorch_model-00002-of-00003.bin",
228
+ "backbone.blocks.23.filter.residues": "pytorch_model-00002-of-00003.bin",
229
+ "backbone.blocks.23.filter.short_filter_bias": "pytorch_model-00002-of-00003.bin",
230
+ "backbone.blocks.23.filter.short_filter_weight": "pytorch_model-00002-of-00003.bin",
231
+ "backbone.blocks.23.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
232
+ "backbone.blocks.23.mlp.l2.weight": "pytorch_model-00002-of-00003.bin",
233
+ "backbone.blocks.23.mlp.l3.weight": "pytorch_model-00002-of-00003.bin",
234
+ "backbone.blocks.23.out_filter_dense.bias": "pytorch_model-00002-of-00003.bin",
235
+ "backbone.blocks.23.out_filter_dense.weight": "pytorch_model-00002-of-00003.bin",
236
+ "backbone.blocks.23.post_norm.scale": "pytorch_model-00002-of-00003.bin",
237
+ "backbone.blocks.23.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
238
+ "backbone.blocks.23.projections.bias": "pytorch_model-00002-of-00003.bin",
239
+ "backbone.blocks.23.projections.weight": "pytorch_model-00002-of-00003.bin",
240
+ "backbone.blocks.24.inner_mha_cls.Wqkv.bias": "pytorch_model-00002-of-00003.bin",
241
+ "backbone.blocks.24.inner_mha_cls.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
242
+ "backbone.blocks.24.inner_mha_cls.out_proj.bias": "pytorch_model-00002-of-00003.bin",
243
+ "backbone.blocks.24.inner_mha_cls.out_proj.weight": "pytorch_model-00002-of-00003.bin",
244
+ "backbone.blocks.24.inner_mha_cls.rotary_emb.inv_freq": "pytorch_model-00002-of-00003.bin",
245
+ "backbone.blocks.24.mlp.l1.weight": "pytorch_model-00002-of-00003.bin",
246
+ "backbone.blocks.24.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
247
+ "backbone.blocks.24.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
248
+ "backbone.blocks.24.post_norm.scale": "pytorch_model-00002-of-00003.bin",
249
+ "backbone.blocks.24.pre_norm.scale": "pytorch_model-00002-of-00003.bin",
250
+ "backbone.blocks.25.filter.D": "pytorch_model-00003-of-00003.bin",
251
+ "backbone.blocks.25.filter.poles": "pytorch_model-00003-of-00003.bin",
252
+ "backbone.blocks.25.filter.residues": "pytorch_model-00003-of-00003.bin",
253
+ "backbone.blocks.25.filter.short_filter_bias": "pytorch_model-00003-of-00003.bin",
254
+ "backbone.blocks.25.filter.short_filter_weight": "pytorch_model-00003-of-00003.bin",
255
+ "backbone.blocks.25.mlp.l1.weight": "pytorch_model-00003-of-00003.bin",
256
+ "backbone.blocks.25.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
257
+ "backbone.blocks.25.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
258
+ "backbone.blocks.25.out_filter_dense.bias": "pytorch_model-00003-of-00003.bin",
259
+ "backbone.blocks.25.out_filter_dense.weight": "pytorch_model-00003-of-00003.bin",
260
+ "backbone.blocks.25.post_norm.scale": "pytorch_model-00003-of-00003.bin",
261
+ "backbone.blocks.25.pre_norm.scale": "pytorch_model-00003-of-00003.bin",
262
+ "backbone.blocks.25.projections.bias": "pytorch_model-00003-of-00003.bin",
263
+ "backbone.blocks.25.projections.weight": "pytorch_model-00003-of-00003.bin",
264
+ "backbone.blocks.26.filter.D": "pytorch_model-00003-of-00003.bin",
265
+ "backbone.blocks.26.filter.poles": "pytorch_model-00003-of-00003.bin",
266
+ "backbone.blocks.26.filter.residues": "pytorch_model-00003-of-00003.bin",
267
+ "backbone.blocks.26.filter.short_filter_bias": "pytorch_model-00003-of-00003.bin",
268
+ "backbone.blocks.26.filter.short_filter_weight": "pytorch_model-00003-of-00003.bin",
269
+ "backbone.blocks.26.mlp.l1.weight": "pytorch_model-00003-of-00003.bin",
270
+ "backbone.blocks.26.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
271
+ "backbone.blocks.26.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
272
+ "backbone.blocks.26.out_filter_dense.bias": "pytorch_model-00003-of-00003.bin",
273
+ "backbone.blocks.26.out_filter_dense.weight": "pytorch_model-00003-of-00003.bin",
274
+ "backbone.blocks.26.post_norm.scale": "pytorch_model-00003-of-00003.bin",
275
+ "backbone.blocks.26.pre_norm.scale": "pytorch_model-00003-of-00003.bin",
276
+ "backbone.blocks.26.projections.bias": "pytorch_model-00003-of-00003.bin",
277
+ "backbone.blocks.26.projections.weight": "pytorch_model-00003-of-00003.bin",
278
+ "backbone.blocks.27.filter.D": "pytorch_model-00003-of-00003.bin",
279
+ "backbone.blocks.27.filter.poles": "pytorch_model-00003-of-00003.bin",
280
+ "backbone.blocks.27.filter.residues": "pytorch_model-00003-of-00003.bin",
281
+ "backbone.blocks.27.filter.short_filter_bias": "pytorch_model-00003-of-00003.bin",
282
+ "backbone.blocks.27.filter.short_filter_weight": "pytorch_model-00003-of-00003.bin",
283
+ "backbone.blocks.27.mlp.l1.weight": "pytorch_model-00003-of-00003.bin",
284
+ "backbone.blocks.27.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
285
+ "backbone.blocks.27.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
286
+ "backbone.blocks.27.out_filter_dense.bias": "pytorch_model-00003-of-00003.bin",
287
+ "backbone.blocks.27.out_filter_dense.weight": "pytorch_model-00003-of-00003.bin",
288
+ "backbone.blocks.27.post_norm.scale": "pytorch_model-00003-of-00003.bin",
289
+ "backbone.blocks.27.pre_norm.scale": "pytorch_model-00003-of-00003.bin",
290
+ "backbone.blocks.27.projections.bias": "pytorch_model-00003-of-00003.bin",
291
+ "backbone.blocks.27.projections.weight": "pytorch_model-00003-of-00003.bin",
292
+ "backbone.blocks.28.filter.D": "pytorch_model-00003-of-00003.bin",
293
+ "backbone.blocks.28.filter.poles": "pytorch_model-00003-of-00003.bin",
294
+ "backbone.blocks.28.filter.residues": "pytorch_model-00003-of-00003.bin",
295
+ "backbone.blocks.28.filter.short_filter_bias": "pytorch_model-00003-of-00003.bin",
296
+ "backbone.blocks.28.filter.short_filter_weight": "pytorch_model-00003-of-00003.bin",
297
+ "backbone.blocks.28.mlp.l1.weight": "pytorch_model-00003-of-00003.bin",
298
+ "backbone.blocks.28.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
299
+ "backbone.blocks.28.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
300
+ "backbone.blocks.28.out_filter_dense.bias": "pytorch_model-00003-of-00003.bin",
301
+ "backbone.blocks.28.out_filter_dense.weight": "pytorch_model-00003-of-00003.bin",
302
+ "backbone.blocks.28.post_norm.scale": "pytorch_model-00003-of-00003.bin",
303
+ "backbone.blocks.28.pre_norm.scale": "pytorch_model-00003-of-00003.bin",
304
+ "backbone.blocks.28.projections.bias": "pytorch_model-00003-of-00003.bin",
305
+ "backbone.blocks.28.projections.weight": "pytorch_model-00003-of-00003.bin",
306
+ "backbone.blocks.29.filter.D": "pytorch_model-00003-of-00003.bin",
307
+ "backbone.blocks.29.filter.poles": "pytorch_model-00003-of-00003.bin",
308
+ "backbone.blocks.29.filter.residues": "pytorch_model-00003-of-00003.bin",
309
+ "backbone.blocks.29.filter.short_filter_bias": "pytorch_model-00003-of-00003.bin",
310
+ "backbone.blocks.29.filter.short_filter_weight": "pytorch_model-00003-of-00003.bin",
311
+ "backbone.blocks.29.mlp.l1.weight": "pytorch_model-00003-of-00003.bin",
312
+ "backbone.blocks.29.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
313
+ "backbone.blocks.29.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
314
+ "backbone.blocks.29.out_filter_dense.bias": "pytorch_model-00003-of-00003.bin",
315
+ "backbone.blocks.29.out_filter_dense.weight": "pytorch_model-00003-of-00003.bin",
316
+ "backbone.blocks.29.post_norm.scale": "pytorch_model-00003-of-00003.bin",
317
+ "backbone.blocks.29.pre_norm.scale": "pytorch_model-00003-of-00003.bin",
318
+ "backbone.blocks.29.projections.bias": "pytorch_model-00003-of-00003.bin",
319
+ "backbone.blocks.29.projections.weight": "pytorch_model-00003-of-00003.bin",
320
+ "backbone.blocks.3.filter.D": "pytorch_model-00001-of-00003.bin",
321
+ "backbone.blocks.3.filter.poles": "pytorch_model-00001-of-00003.bin",
322
+ "backbone.blocks.3.filter.residues": "pytorch_model-00001-of-00003.bin",
323
+ "backbone.blocks.3.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
324
+ "backbone.blocks.3.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
325
+ "backbone.blocks.3.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
326
+ "backbone.blocks.3.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
327
+ "backbone.blocks.3.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
328
+ "backbone.blocks.3.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
329
+ "backbone.blocks.3.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
330
+ "backbone.blocks.3.post_norm.scale": "pytorch_model-00001-of-00003.bin",
331
+ "backbone.blocks.3.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
332
+ "backbone.blocks.3.projections.bias": "pytorch_model-00001-of-00003.bin",
333
+ "backbone.blocks.3.projections.weight": "pytorch_model-00001-of-00003.bin",
334
+ "backbone.blocks.30.filter.D": "pytorch_model-00003-of-00003.bin",
335
+ "backbone.blocks.30.filter.poles": "pytorch_model-00003-of-00003.bin",
336
+ "backbone.blocks.30.filter.residues": "pytorch_model-00003-of-00003.bin",
337
+ "backbone.blocks.30.filter.short_filter_bias": "pytorch_model-00003-of-00003.bin",
338
+ "backbone.blocks.30.filter.short_filter_weight": "pytorch_model-00003-of-00003.bin",
339
+ "backbone.blocks.30.mlp.l1.weight": "pytorch_model-00003-of-00003.bin",
340
+ "backbone.blocks.30.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
341
+ "backbone.blocks.30.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
342
+ "backbone.blocks.30.out_filter_dense.bias": "pytorch_model-00003-of-00003.bin",
343
+ "backbone.blocks.30.out_filter_dense.weight": "pytorch_model-00003-of-00003.bin",
344
+ "backbone.blocks.30.post_norm.scale": "pytorch_model-00003-of-00003.bin",
345
+ "backbone.blocks.30.pre_norm.scale": "pytorch_model-00003-of-00003.bin",
346
+ "backbone.blocks.30.projections.bias": "pytorch_model-00003-of-00003.bin",
347
+ "backbone.blocks.30.projections.weight": "pytorch_model-00003-of-00003.bin",
348
+ "backbone.blocks.31.filter.D": "pytorch_model-00003-of-00003.bin",
349
+ "backbone.blocks.31.filter.poles": "pytorch_model-00003-of-00003.bin",
350
+ "backbone.blocks.31.filter.residues": "pytorch_model-00003-of-00003.bin",
351
+ "backbone.blocks.31.filter.short_filter_bias": "pytorch_model-00003-of-00003.bin",
352
+ "backbone.blocks.31.filter.short_filter_weight": "pytorch_model-00003-of-00003.bin",
353
+ "backbone.blocks.31.mlp.l1.weight": "pytorch_model-00003-of-00003.bin",
354
+ "backbone.blocks.31.mlp.l2.weight": "pytorch_model-00003-of-00003.bin",
355
+ "backbone.blocks.31.mlp.l3.weight": "pytorch_model-00003-of-00003.bin",
356
+ "backbone.blocks.31.out_filter_dense.bias": "pytorch_model-00003-of-00003.bin",
357
+ "backbone.blocks.31.out_filter_dense.weight": "pytorch_model-00003-of-00003.bin",
358
+ "backbone.blocks.31.post_norm.scale": "pytorch_model-00003-of-00003.bin",
359
+ "backbone.blocks.31.pre_norm.scale": "pytorch_model-00003-of-00003.bin",
360
+ "backbone.blocks.31.projections.bias": "pytorch_model-00003-of-00003.bin",
361
+ "backbone.blocks.31.projections.weight": "pytorch_model-00003-of-00003.bin",
362
+ "backbone.blocks.4.filter.D": "pytorch_model-00001-of-00003.bin",
363
+ "backbone.blocks.4.filter.poles": "pytorch_model-00001-of-00003.bin",
364
+ "backbone.blocks.4.filter.residues": "pytorch_model-00001-of-00003.bin",
365
+ "backbone.blocks.4.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
366
+ "backbone.blocks.4.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
367
+ "backbone.blocks.4.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
368
+ "backbone.blocks.4.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
369
+ "backbone.blocks.4.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
370
+ "backbone.blocks.4.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
371
+ "backbone.blocks.4.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
372
+ "backbone.blocks.4.post_norm.scale": "pytorch_model-00001-of-00003.bin",
373
+ "backbone.blocks.4.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
374
+ "backbone.blocks.4.projections.bias": "pytorch_model-00001-of-00003.bin",
375
+ "backbone.blocks.4.projections.weight": "pytorch_model-00001-of-00003.bin",
376
+ "backbone.blocks.5.filter.D": "pytorch_model-00001-of-00003.bin",
377
+ "backbone.blocks.5.filter.poles": "pytorch_model-00001-of-00003.bin",
378
+ "backbone.blocks.5.filter.residues": "pytorch_model-00001-of-00003.bin",
379
+ "backbone.blocks.5.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
380
+ "backbone.blocks.5.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
381
+ "backbone.blocks.5.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
382
+ "backbone.blocks.5.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
383
+ "backbone.blocks.5.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
384
+ "backbone.blocks.5.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
385
+ "backbone.blocks.5.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
386
+ "backbone.blocks.5.post_norm.scale": "pytorch_model-00001-of-00003.bin",
387
+ "backbone.blocks.5.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
388
+ "backbone.blocks.5.projections.bias": "pytorch_model-00001-of-00003.bin",
389
+ "backbone.blocks.5.projections.weight": "pytorch_model-00001-of-00003.bin",
390
+ "backbone.blocks.6.filter.D": "pytorch_model-00001-of-00003.bin",
391
+ "backbone.blocks.6.filter.poles": "pytorch_model-00001-of-00003.bin",
392
+ "backbone.blocks.6.filter.residues": "pytorch_model-00001-of-00003.bin",
393
+ "backbone.blocks.6.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
394
+ "backbone.blocks.6.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
395
+ "backbone.blocks.6.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
396
+ "backbone.blocks.6.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
397
+ "backbone.blocks.6.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
398
+ "backbone.blocks.6.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
399
+ "backbone.blocks.6.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
400
+ "backbone.blocks.6.post_norm.scale": "pytorch_model-00001-of-00003.bin",
401
+ "backbone.blocks.6.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
402
+ "backbone.blocks.6.projections.bias": "pytorch_model-00001-of-00003.bin",
403
+ "backbone.blocks.6.projections.weight": "pytorch_model-00001-of-00003.bin",
404
+ "backbone.blocks.7.filter.D": "pytorch_model-00001-of-00003.bin",
405
+ "backbone.blocks.7.filter.poles": "pytorch_model-00001-of-00003.bin",
406
+ "backbone.blocks.7.filter.residues": "pytorch_model-00001-of-00003.bin",
407
+ "backbone.blocks.7.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
408
+ "backbone.blocks.7.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
409
+ "backbone.blocks.7.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
410
+ "backbone.blocks.7.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
411
+ "backbone.blocks.7.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
412
+ "backbone.blocks.7.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
413
+ "backbone.blocks.7.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
414
+ "backbone.blocks.7.post_norm.scale": "pytorch_model-00001-of-00003.bin",
415
+ "backbone.blocks.7.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
416
+ "backbone.blocks.7.projections.bias": "pytorch_model-00001-of-00003.bin",
417
+ "backbone.blocks.7.projections.weight": "pytorch_model-00001-of-00003.bin",
418
+ "backbone.blocks.8.inner_mha_cls.Wqkv.bias": "pytorch_model-00001-of-00003.bin",
419
+ "backbone.blocks.8.inner_mha_cls.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
420
+ "backbone.blocks.8.inner_mha_cls.out_proj.bias": "pytorch_model-00001-of-00003.bin",
421
+ "backbone.blocks.8.inner_mha_cls.out_proj.weight": "pytorch_model-00001-of-00003.bin",
422
+ "backbone.blocks.8.inner_mha_cls.rotary_emb.inv_freq": "pytorch_model-00001-of-00003.bin",
423
+ "backbone.blocks.8.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
424
+ "backbone.blocks.8.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
425
+ "backbone.blocks.8.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
426
+ "backbone.blocks.8.post_norm.scale": "pytorch_model-00001-of-00003.bin",
427
+ "backbone.blocks.8.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
428
+ "backbone.blocks.9.filter.D": "pytorch_model-00001-of-00003.bin",
429
+ "backbone.blocks.9.filter.poles": "pytorch_model-00001-of-00003.bin",
430
+ "backbone.blocks.9.filter.residues": "pytorch_model-00001-of-00003.bin",
431
+ "backbone.blocks.9.filter.short_filter_bias": "pytorch_model-00001-of-00003.bin",
432
+ "backbone.blocks.9.filter.short_filter_weight": "pytorch_model-00001-of-00003.bin",
433
+ "backbone.blocks.9.mlp.l1.weight": "pytorch_model-00001-of-00003.bin",
434
+ "backbone.blocks.9.mlp.l2.weight": "pytorch_model-00001-of-00003.bin",
435
+ "backbone.blocks.9.mlp.l3.weight": "pytorch_model-00001-of-00003.bin",
436
+ "backbone.blocks.9.out_filter_dense.bias": "pytorch_model-00001-of-00003.bin",
437
+ "backbone.blocks.9.out_filter_dense.weight": "pytorch_model-00001-of-00003.bin",
438
+ "backbone.blocks.9.post_norm.scale": "pytorch_model-00001-of-00003.bin",
439
+ "backbone.blocks.9.pre_norm.scale": "pytorch_model-00001-of-00003.bin",
440
+ "backbone.blocks.9.projections.bias": "pytorch_model-00001-of-00003.bin",
441
+ "backbone.blocks.9.projections.weight": "pytorch_model-00001-of-00003.bin",
442
+ "backbone.embedding_layer.weight": "pytorch_model-00001-of-00003.bin",
443
+ "backbone.norm.scale": "pytorch_model-00001-of-00003.bin",
444
+ "backbone.unembed.weight": "pytorch_model-00001-of-00003.bin"
445
+ }
446
+ }